English
Related papers

Related papers: Flow-Guided Transformer for Video Inpainting

200 papers

In this paper, we present the numerical solution of two-phase flow problems of engineering significance with a space-time finite element method that allows for local temporal refinement. Our basis is the method presented in [3], which…

Computational Engineering, Finance, and Science · Computer Science 2019-03-22 Violeta Karyofylli , Markus Frings , Stefanie Elgeti , Marek Behr

Image inpainting for completing complicated semantic environments and diverse hole patterns of corrupted images is challenging even for state-of-the-art learning-based inpainting methods trained on large-scale data. A reference image…

Computer Vision and Pattern Recognition · Computer Science 2025-02-12 Taorong Liu , Liang Liao , Delin Chen , Jing Xiao , Zheng Wang , Chia-Wen Lin , Shin'ichi Satoh

Video restoration aims at restoring multiple high-quality frames from multiple low-quality frames. Existing video restoration methods generally fall into two extreme cases, i.e., they either restore all frames in parallel or restore the…

Computer Vision and Pattern Recognition · Computer Science 2022-11-15 Jingyun Liang , Yuchen Fan , Xiaoyu Xiang , Rakesh Ranjan , Eddy Ilg , Simon Green , Jiezhang Cao , Kai Zhang , Radu Timofte , Luc Van Gool

Vision sensors are widely applied in vehicles, robots, and roadside infrastructure. However, due to limitations in hardware cost and system size, camera Field-of-View (FoV) is often restricted and may not provide sufficient coverage.…

Computer Vision and Pattern Recognition · Computer Science 2024-06-25 Hao Shi , Qi Jiang , Kailun Yang , Xiaoting Yin , Ze Wang , Kaiwei Wang

Fluid motion can be considered as a point cloud transformation when using the SPH method. Compared to traditional numerical analysis methods, using machine learning techniques to learn physics simulations can achieve near-accurate results,…

Computer Vision and Pattern Recognition · Computer Science 2024-04-19 Yu Chen , Shuai Zheng , Menglong Jin , Yan Chang , Nianyi Wang

In this work, we introduce FluidsFormer: a transformer-based approach for fluid interpolation within a continuous-time framework. By combining the capabilities of PITT and a residual neural network (RNN), we analytically predict the…

Machine Learning · Computer Science 2024-06-13 Bruno Roy

Traffic flow forecasting is a crucial task in transportation management and planning. The main challenges for traffic flow forecasting are that (1) as the length of prediction time increases, the accuracy of prediction will decrease; (2)…

Artificial Intelligence · Computer Science 2024-05-13 Jianli Xiao , Baichao Long

We present a convolution-free approach to video classification built exclusively on self-attention over space and time. Our method, named "TimeSformer," adapts the standard Transformer architecture to video by enabling spatiotemporal…

Computer Vision and Pattern Recognition · Computer Science 2021-06-10 Gedas Bertasius , Heng Wang , Lorenzo Torresani

Deep learning models, in particular \textit{image} models, have recently gained generalisability and robustness. %are becoming more general and robust by the day. In this work, we propose to exploit such advances in the realm of…

Computer Vision and Pattern Recognition · Computer Science 2024-11-05 Tanay Agrawal , Abid Ali , Antitza Dantcheva , Francois Bremond

This paper introduces Generalized Attention Flow (GAF), a novel feature attribution method for Transformer-based models to address the limitations of current approaches. By extending Attention Flow and replacing attention weights with the…

Machine Learning · Computer Science 2025-02-25 Behrooz Azarkhalili , Maxwell Libbrecht

Deep neural networks, especially transformer-based architectures, have achieved remarkable success in semantic segmentation for environmental perception. However, existing models process video frames independently, thus failing to leverage…

Computer Vision and Pattern Recognition · Computer Science 2026-03-23 Serin Varghese , Kevin Ross , Fabian Hueger , Kira Maag

In this paper, we consider the task of unsupervised object discovery in videos. Previous works have shown promising results via processing optical flows to segment objects. However, taking flow as input brings about two drawbacks. First,…

Computer Vision and Pattern Recognition · Computer Science 2022-10-04 Shuangrui Ding , Weidi Xie , Yabo Chen , Rui Qian , Xiaopeng Zhang , Hongkai Xiong , Qi Tian

Dense and versatile image representations underpin the success of virtually all computer vision applications. However, state-of-the-art networks, such as transformers, produce low-resolution feature grids, which are suboptimal for dense…

Computer Vision and Pattern Recognition · Computer Science 2025-11-12 Nikita Araslanov , Anna Sonnweber , Daniel Cremers

3D occupancy, an advanced perception technology for driving scenarios, represents the entire scene without distinguishing between foreground and background by quantifying the physical space into a grid map. The widely adopted…

Computer Vision and Pattern Recognition · Computer Science 2024-07-15 Jinke Li , Xiao He , Chonghua Zhou , Xiaoqiang Cheng , Yang Wen , Dan Zhang

Image inpainting is an underdetermined inverse problem, which naturally allows diverse contents to fill up the missing or corrupted regions realistically. Prevalent approaches using convolutional neural networks (CNNs) can synthesize…

Computer Vision and Pattern Recognition · Computer Science 2021-06-02 Yingchen Yu , Fangneng Zhan , Rongliang Wu , Jianxiong Pan , Kaiwen Cui , Shijian Lu , Feiying Ma , Xuansong Xie , Chunyan Miao

Applying image processing algorithms independently to each frame of a video often leads to undesired inconsistent results over time. Developing temporally consistent video-based extensions, however, requires domain knowledge for individual…

Computer Vision and Pattern Recognition · Computer Science 2018-08-02 Wei-Sheng Lai , Jia-Bin Huang , Oliver Wang , Eli Shechtman , Ersin Yumer , Ming-Hsuan Yang

Recent video inpainting algorithms integrate flow-based pixel propagation with transformer-based generation to leverage optical flow for restoring textures and objects using information from neighboring frames, while completing masked…

Computer Vision and Pattern Recognition · Computer Science 2025-01-20 Xiaowen Li , Haolan Xue , Peiran Ren , Liefeng Bo

Transformer-based methods have shown impressive performance in low-level vision tasks, such as image super-resolution. However, we find that these networks can only utilize a limited spatial range of input information through attribution…

Image and Video Processing · Electrical Eng. & Systems 2023-03-21 Xiangyu Chen , Xintao Wang , Jiantao Zhou , Yu Qiao , Chao Dong

How to efficiently utilize temporal information to recover videos in a consistent way is the main issue for video inpainting problems. Conventional 2D CNNs have achieved good performance on image inpainting but often lead to temporally…

Computer Vision and Pattern Recognition · Computer Science 2025-05-14 Ya-Liang Chang , Zhe Yu Liu , Kuan-Ying Lee , Winston Hsu

This paper addresses fast semantic segmentation on video.Video segmentation often calls for real-time, or even fasterthan real-time, processing. One common recipe for conserving computation arising from feature extraction is to propagate…

Computer Vision and Pattern Recognition · Computer Science 2021-06-09 Shih-Po Lee , Si-Cun Chen , Wen-Hsiao Peng